SKILLEMALL.ai
GitHub ↗ RU Sign in

AC dingtalk-file-send

Upload and send files to DingTalk users. Auto-detects account from current session. Use when: user asks to send/forward a file/document/PDF/image via DingTalk.

ClawHub Agent Skills author: kenriou v1.2.2 MIT-0 2 files body ≈ 2 429 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
94
Quality 40%
87
Run on models
none yet
Process rating
C
59/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Exfiltration exfil-secret-in-url SKILL.md:132
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      UPLOAD_RESULT=$(curl -s -X POST "https://oapi.dingtalk.com/media/upload?access_token=…&type=file&robotCode=…" \
      placeholder
    • low Exfiltration net-credential-use SKILL.md:132
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      UPLOAD_RESULT=$(curl -s -X POST "https://oapi.dingtalk.com/media/upload?access_token=…&type=file&robotCode=…" \
      vendor-host
    • low Exfiltration exfil-secret-in-url SKILL.md:253
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      UPLOAD_RESULT=$(curl -s -X POST "https://oapi.dingtalk.com/media/upload?access_token=…&type=file&robotCode=…" \
      placeholder
    • low Exfiltration net-credential-use SKILL.md:253
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      UPLOAD_RESULT=$(curl -s -X POST "https://oapi.dingtalk.com/media/upload?access_token=…&type=file&robotCode=…" \
      vendor-host
    • low Exfiltration exfil-secret-in-url SKILL.md:318
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      curl -s -X GET "https://api.dingtalk.com/v1.0/robot/oToMessages/status?processQueryKey=…" \
      vendor-hostquoted
    • low Exfiltration net-credential-use SKILL.md:318
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X GET "https://api.dingtalk.com/v1.0/robot/oToMessages/status?processQueryKey=…" \
      vendor-host

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 5 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2429 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 159: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 17 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This skill is a DingTalk file-sending helper that does what it claims, but users should verify the file, account, and recipient before use.
    LLM: benign (high) · VirusTotal: · 29 May 2026